检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Juneja, Sonam Bhati, Bhoopesh Singh Atwal, Shikha Anand, Monika Maiti, Souvik Chandigarh University Dept. of Computer Science and Engineering Gharuan India Iiit Dept. of Computer Science and Engineering Sonepat India

ISBN: (纸本)9798350371055

The difficulties and ramifications of PCOS, which affects a sizable portion of women who are of reproductive age, are discussed in this review. The article covers the various clinical manifestations of PCOS, how it affects both reproductive and non-reproductive health, and how it's linked to psychological distress and metabolic disorders. It highlights how critical lifestyle modifications, early detection, and accurate diagnosis are. Additionally, the study presents machine learning techniques for PCOS detection, demonstrating the effectiveness of techniques like Random Forests, CNN, and SVM. An innovative CDSS that uses the Red Deer Algorithm shows encouraging accuracy. The necessity of continued research, diversified datasets, and cooperative efforts to enhance PCOS detection at the nexus of technology and healthcare is highlighted in the abstract's conclusion. © 2024 IEEE.

关键词： Deep Learning KNN Machine Learning PCOS Random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

Architectural Model of Deep Convolution Neural Network Approach for Brain Tumor Prediction

Architectural Model of Deep Convolution Neural Network Appro...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Panigrahi, Raghunath Sahu, Rekha Nayak, Suvendu Chandan Kabat, Manas Ranjan IMIT Dept. of Computer Science and Engineering Cuttack India Silicon University Dept. of Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350369175

Magnetic Resonance Imaging (MRI) is most commonly used technique to detect a tumor by physicians in medical science. The MRI images are three-dimensional images with the number of slices that are analyzed to identify the defective cells in the naked eye that leads to a time-consuming process. Machine Learning (ML) techniques are investigated as a solution to improve tumor identification in a better way. Early and accurate detection is crucial for effective treatment planning and improving patient outcomes. Traditionally, brain tumor diagnosis relies on manual analysis of MRI (Magnetic Resonance Imaging) scans by radiologists, which can be time-consuming and prone to human error. The advent of deep learning, particularly Convolutional Neural Networks (CNNs), has opened new avenues for automating and improving the accuracy of brain tumor prediction. In this paper, we study the Convolutional Neural Network(CNN) model which is popular in image analysis. Similar way, we develop a CNN model to process and classify the MRI images to detect the type of brain tumor. We examine the model's performance by using 5712 MRI images from a standard dataset available in the public domain. The aim of the work is to classify the tumor in four classes like: Glioma, Meningioma, Pituitary and No Tumour using the proposed CNN model. Our model follows data preprocessing, image encoding, filtering and classification. The proposed model scores 78% accuracy as its performance in the dataset which needs more investigations and comparison with other techniques in further study. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tail Optimality of the Nudge-M Scheduling Algorithm

引用

Performance Evaluation Review 2024年第2期52卷 21-23页

作者： Charlet, Nils Van Houdt, Benny Dept. Computer Science University of Antwerp Antwerp Belgium

Recently it was shown that the response time of First-Come- First-Served (FCFS) scheduling can be stochastically and asymptotically improved upon by the Nudge scheduling algorithm in case of light-tailed job size distributions. Such improvements are feasible even when the jobs are partitioned into two types and the scheduler only has information about the type of incoming jobs (but not their size). In this paper we introduce Nudge-M scheduling, where basically any incoming type-1 job is allowed to pass any type-2 job that is still waiting in the queue given that it arrived as one of the last M jobs. We prove that Nudge- M has an asymptotically optimal response time within a large family of Nudge scheduling algorithms when job sizes are light-tailed. Simple explicit results for the the prefactor of Nudge-M are derived as well as explicit results for the optimal parameter M. An expression for the prefactor that only depends on the type-1 and type-2 mean job sizes and the fraction of type-1 jobs is presented in the heavy traffic setting. © 2024 Copyright is held by the owner/author(s).

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Trust Based Cooperative Secure Routing Protocols for Internet of Things (IoT) 2

Trust Based Cooperative Secure Routing Protocols for Interne...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Mekala, Sagar Ramji, Bhukya CVR College of Engineering Dept. of Computer Science and Engineering Hyderabad India Kakatiya Institute of Technology and Science Dept. of Computer Science and Engineering Hanmakonda India

ISBN: (纸本)9798350366570

The Internet of Things has rapidly emerged and continues to create services, software, sensors-embedded devices, and protocols. IoT allows physical objects to communicate, exchange information, and make decisions while performing critical jobs. The Internet of Things is enhanced by wireless sensor networks, which serve as a continuous layer. To gain adoption and spread, Internet of things-based sensor networks must overcome serious general and specialized risks and technological hurdles. The main drawbacks of wireless sensor networks are insufficient resources. Internet of Things (IOT)-based Wireless Sensor Networks have issues in energy consumption, longevity, throughput, routing, and security. The goal of this effort was to enhance network longevity, throughput, packet latency/loss, and better encounters with hostile nodes. Consider wireless energy harvesting in the proposed three-layer cluster-based wireless sensor network routing protocol to enhance network lifespan. The proposed approach is a Trust based Cooperative Secure Routing Protocol (TCSRP) technique with security system to obtain malicious activities of objects and to slant them into blacklist. Finally, experiments were done to test the methodology. It outperforms most traditional routing protocols like AODV, DSR, and DSDV. © 2024 IEEE.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

An Effective Deep Learning Approach for Kidney Stone Detection in CT Scan Images using Convolutional Neural Network

An Effective Deep Learning Approach for Kidney Stone Detecti...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Islam, Md. Nurul Khan Chowdhury, Md. Fuad Hasan Nusrat, Fariha University of Scholars Dept. of Computer Science and Engineering Dhaka Bangladesh United International University Dept. of Computer Science and Engineering Dhaka Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331529765

Kidney stones represent a significant global health concern, frequently causing individuals to seek immediate medical care due to intense pain. Radiological imaging modalities are one of the most common modes of diagnosis, but specialist interpretation is always important for accuracy. In this paper, we present computer vision in an automated kidney stone detection system that involves five stages: loading the dataset, preprocessing data, loading the InceptionV3 model, predicting, and evaluating performance. Various methods of preprocessing and data augmentation were utilized to make the model less biased and more robust. This study uses the InceptionV3 architecture to classify kidney stones in CT scan images of KUB (Kidney, Ureter, and Bladder). We utilize a total dataset of 433 participants, either diagnosed with kidney stones or in a normal state. 278 cases are diagnosed with kidney stones, and 165 are normal cases. The proposed approach achieved an impressive 98.55% accuracy across performance metrics when evaluated on an independent test dataset. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Non-Intrusive Alert For Drivers With Fatigue 4

Non-Intrusive Alert For Drivers With Fatigue

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Amrutha, K. Shreekumar, T. Resmi, K.R. Vineetha, K.R. Dept. of Computer Science Bangalore India Mite Dept of Computer Science and Engineering Mangalore India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354218

Fatigue during driving significantly impairs a driver's reaction time, awareness, and decision-making abilities, leading to an increased risk of accidents. Recognising and mitigating driver fatigue is crucial for enhancing road safety and preventing potential collisions. This research introduces a non-intrusive method to reduce road accidents caused by driver fatigue. Recognising that accidents often occur due to lapses in driver alertness, the system utilises an affordable, high-quality webcam and dashcam. The approach involves extracting essential information through a multi-stage monitoring process to evaluate the driver's state thoroughly. The study includes a detailed analysis of webcam specifications, such as resolution, frame rate, and additional features. It also compares the traditional cascading technique with the advanced MediaPipe method, incorporating facial recognition, eye movement tracking, and head position analysis to detect driver fatigue accurately. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Defending Learning Systems Against Mean-Shift Perturbations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年 1-13页

作者： Roy, Arunava Dasgupta, Dipankar Dept. of Computer Science The University of Memphis Memphis Tennessee USA

Evasion attacks on cyber-enabled machine learning (ML) models have recently gained significant traction for their ability to swiftly compel ML models to deviate from their original decisions without substantially affecting model accuracy during the testing phase. In this article, we initially present a meticulously formulated theoretical framework for a novel and potent evasion attack, leveraging mean-shift perturbation. This attack demonstrates remarkable efficiency in deceiving a wide array of ML models. Subsequently, the urgency of fortifying against such evasion attacks is underscored. It’s worth noting that existing defenses are predominantly model-driven, and their efficacy diminishes when concurrently deployed as a universal defense against both poisoning and evasion attacks. Moreover, empirical evidence from various studies suggests that a single defense mechanism falls short in safeguarding learning models against the myriad forms of adversarial attacks. To alleviate these challenges, we introduced Adaptive Ensemble of Filters (AEF), a defense framework characterized by its robust, transferable, model-agnostic, input distribution-independent, and cross-model-supportive nature. The AEF strategically selects filters to safeguard a target ML model from various well-known poisoning (e.g., Metapoison) and evasion (utilizing mean-shift perturbations, JSMA, FGSM, PGD, BIM, and C&W) attacks, establishing itself as a universal defense against diverse adversarial attacks. Theoretical analysis assures the existence of optimal filter ensembles across different input distributions and adversarial attack landscapes, without encountering mode collapses and vanishing gradients. Our claims are substantiated through validation on three publicly available image datasets—MNIST, CIFAR-10, and EuroSAT. IEEE

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

A comprehensive step of XAI for Bengali and English text detection and recognition from natural scene images 2

A comprehensive step of XAI for Bengali and English text det...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Dutta, Mithun Das, Utpol Kanti Das, Jugal Krishna Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati Bangladesh Jahangirnagar University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350367461

A critical first step in many applications, including augmented reality, document analysis, and scene comprehension, is text detection from images. Even though text identification for the English language has advanced significantly, there are particular difficulties when applying these methods to languages such as Bengali because of variations in script, morphology, and typographic characteristics. This article offers a wonderful method for leveraging the Faster R-CNN framework to identify and categorize text from images that contain Bengali and English sentences. The study utilizes a dataset named "Bengali and English text image dataset (BETID)"that consists of images with text in both Bengali and English scripts, taken from a variety of sources such as books, documents, natural scenes, internet images, and landscapes. Pre-processing methods are used to improve the resilience and generalization of the model, including image scaling, normalization, and augmentation. The Faster R-CNN architecture is tuned and trained to identify text regions in images and categorize Bengali or English text. The performance of the text Classification model is evaluated using evaluation measures such as accuracy on the BETID dataset. The proposed Faster R-CNN model achieved an average of 97.90% accuracy, which is better than other deep learning models. Empirical findings showcase the capacity of transfer learning to alleviate data scarcity concerns and enhance text detection precision for low-resource languages such as Bengali.) © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired Heuristic Optimization-based Cascaded Network for Diabetic Retinopathy Screening 3

Bio-inspired Heuristic Optimization-based Cascaded Network f...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Shuvo, Eshat Ahmad Rahman, Wahidur Hossain, Md Shakhawat Islam, Md. Tarequl Iqbal, Md. Sadiq Bangladesh University Dept. of Computer Science and Engineering Adabor Bangladesh Uttara University Dept. of Computer Science and Engineering Uttara Dhaka Bangladesh Center Independent University Dept. of Computer Science & Engineering & RIoT Bangladesh Khwaja Yunus Ali University Dept. of Computer Science & Engineering Sirajganj Bangladesh

ISBN: (纸本)9798350388282

Diabetic retinopathy (DR) is a common yet fatal complication of diabetic patients in which high levels of blood sugar damage the blood vessels in the retina, the light-sensitive eye tissue crucial for human vision. Early detection and timely intervention are essential to managing DR and preventing severe vision loss. Traditionally, the examination is performed by ophthalmologists manually examining the retinal fundus images to check for signs of DR. This approach is helpful but subjective, time-consuming and tedious. Artificial intelligence (AI)-guided computer vision has recently become very compelling and practical for image analysis and diagnosis. Existing AI-based methods achieved sufficient accuracy at the cost of high computing resources and large datasets. This paper proposes a cascaded network incorporating deep learning and the traditional machine learning approaches with a bio-inspired heuristic optimization algorithm for DR detection from fundus images. The proposed method achieved sufficient accuracy (97.1%) when trained using limited data and low computing machines. The AI models for the cascaded networks were selected through an exhaustive search in which five popular CNN models were used for extracting features;the Bacterial foraging optimization (BFO) was used to determine optimal features, and seven traditional machine models were used to detect the DR. The ResNet50-BFO-SVC cascaded network was found to be most suitable in this study. The proposed cascaded network brings efficiency, accuracy, scalability, and robustness to DR screening. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Secured Entry Control: An IoT and Deep Learning based Mask Detection System for COVID-19 Suspected Patient Screening and Access Regulation 3

Secured Entry Control: An IoT and Deep Learning based Mask D...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Sultana, Abida Peyal, Hasibul Islam Islam, Md. Injamul Abdal, Md. Nazmul Miraz, Shafiun Kontho, Md. Mahin Rahaman Leion, Zannatul Mawa Mamun, Abdul Al Rajshahi University of Engineering & Technology Dept. of Electrical & Computer Engineering Rajshahi Bangladesh Uttara University Dept. of Computer Science & Engineering Dhaka Bangladesh University of Liberal Arts Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi Bangladesh Tejgaon College Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350388282

The new coronavirus SARS-CoV-2, which triggered the COVID-19 pandemic, has had an unparalleled effect on economies, cultures, and world health. In response to the critical need for strict COVID-19 screening systems in public areas, this study presents a creative Secured Entry Control system. Detecting and controlling possible COVID-19 carriers attempting to enter the country is made possible by this system, which makes use of deep learning algorithms and IoT technology. The mask detection algorithm, MobileNetV2 model, has an exceptional validation accuracy of 98.96\%. The model's reliability is supported by performance evaluations using ROC curves, confusion matrix analysis, and an AUC value of 98.96\%, which is close to the optimal AUC score of 100\%. Because MobileNetV2 is well-suited for low-processing devices, it is easy to deploy it on Raspberry Pi, which helps to create an affordable system. Furthermore, by spotting increased body temperatures, a contactless temperature sensor improves the system's ability to identify possible COVID-19 carriers. The functioning of the system is confirmed by the working prototype that is presented in the Experimental Results section. The main goal of this research is to create an autonomous system that is affordable and selectively allows access to people who are less likely to transmit COVID-19 in public areas. To achieve the overall objective of reducing the spread of COVID-19 in public spaces, this research highlights the successful integration of mask identification algorithms and IoT. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：